{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PLN65EJSHVSNZC5RV6O7CEU43G","short_pith_number":"pith:PLN65EJS","schema_version":"1.0","canonical_sha256":"7adbee91323d64dc8bb1af9df1129cd9a36d8ad703af7613723f723c9512828c","source":{"kind":"arxiv","id":"2402.18732","version":1},"attestation_state":"computed","paper":{"title":"GAIA: Categorical Foundations of Generative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Sridhar Mahadevan","submitted_at":"2024-02-28T22:25:02Z","abstract_excerpt":"In this paper, we propose GAIA, a generative AI architecture based on category theory. GAIA is based on a hierarchical model where modules are organized as a simplicial complex. Each simplicial complex updates its internal parameters biased on information it receives from its superior simplices and in turn relays updates to its subordinate sub-simplices. Parameter updates are formulated in terms of lifting diagrams over simplicial sets, where inner and outer horn extensions correspond to different types of learning problems. Backpropagation is modeled as an endofunctor over the category of par"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.18732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-28T22:25:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d5efb85d6e717317b9361609f4f63b013de3bef2e8b6c20e625ba01c2d139178","abstract_canon_sha256":"b39ce5c5c3f932fc5111e1b0702b646595f7d002a6aef4e7c78da48b964cc331"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:26.725404Z","signature_b64":"wUkdtRDZ/ymprzHWfu/9kjCgbG6xsJfN0U9uKXsIdc7TffSmYkGmjHt8e3zXAk7t64cIVJi0gtaD+8bRjsCgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7adbee91323d64dc8bb1af9df1129cd9a36d8ad703af7613723f723c9512828c","last_reissued_at":"2026-07-05T07:50:26.724922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:26.724922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAIA: Categorical Foundations of Generative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Sridhar Mahadevan","submitted_at":"2024-02-28T22:25:02Z","abstract_excerpt":"In this paper, we propose GAIA, a generative AI architecture based on category theory. GAIA is based on a hierarchical model where modules are organized as a simplicial complex. Each simplicial complex updates its internal parameters biased on information it receives from its superior simplices and in turn relays updates to its subordinate sub-simplices. Parameter updates are formulated in terms of lifting diagrams over simplicial sets, where inner and outer horn extensions correspond to different types of learning problems. Backpropagation is modeled as an endofunctor over the category of par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18732","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.18732/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.18732","created_at":"2026-07-05T07:50:26.724981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18732v1","created_at":"2026-07-05T07:50:26.724981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18732","created_at":"2026-07-05T07:50:26.724981+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLN65EJSHVSN","created_at":"2026-07-05T07:50:26.724981+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLN65EJSHVSNZC5R","created_at":"2026-07-05T07:50:26.724981+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLN65EJS","created_at":"2026-07-05T07:50:26.724981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12504","citing_title":"A Type Theory of Sense: Witnessed Choice in Stratified Semantic Spaces","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PLN65EJSHVSNZC5RV6O7CEU43G","json":"https://pith.science/pith/PLN65EJSHVSNZC5RV6O7CEU43G.json","graph_json":"https://pith.science/api/pith-number/PLN65EJSHVSNZC5RV6O7CEU43G/graph.json","events_json":"https://pith.science/api/pith-number/PLN65EJSHVSNZC5RV6O7CEU43G/events.json","paper":"https://pith.science/paper/PLN65EJS"},"agent_actions":{"view_html":"https://pith.science/pith/PLN65EJSHVSNZC5RV6O7CEU43G","download_json":"https://pith.science/pith/PLN65EJSHVSNZC5RV6O7CEU43G.json","view_paper":"https://pith.science/paper/PLN65EJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18732&json=true","fetch_graph":"https://pith.science/api/pith-number/PLN65EJSHVSNZC5RV6O7CEU43G/graph.json","fetch_events":"https://pith.science/api/pith-number/PLN65EJSHVSNZC5RV6O7CEU43G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLN65EJSHVSNZC5RV6O7CEU43G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLN65EJSHVSNZC5RV6O7CEU43G/action/storage_attestation","attest_author":"https://pith.science/pith/PLN65EJSHVSNZC5RV6O7CEU43G/action/author_attestation","sign_citation":"https://pith.science/pith/PLN65EJSHVSNZC5RV6O7CEU43G/action/citation_signature","submit_replication":"https://pith.science/pith/PLN65EJSHVSNZC5RV6O7CEU43G/action/replication_record"}},"created_at":"2026-07-05T07:50:26.724981+00:00","updated_at":"2026-07-05T07:50:26.724981+00:00"}